Random Forest Classification for Surficial Material Mapping in Northern Canada

There is a need at the Geological Survey of Canada to apply improved accuracy assessments of satellite image classification and to support remote predictive mapping techniques for geological map production and field operations. Most existing image classification algorithms, however, lack any robust capabilities for assessing classification accuracy and its variability throughout the landscape. In this study, a random forest classification workflow is introduced to improve understanding of overall image classification accuracy and to better describe its spatial variability across a heterogeneous landscape in Northern Canada.;Random Forest model is a stochastic implementation of classification and regression trees, which is computationally efficient, effectively handles outlier bias can be used on non-parametric data sources. A variable selection methodology and stochastic accuracy assessment for Random Forest is introduced. Random forest provides an enhanced classification compared to the standard maximum likelihood algorithms improving predictive capacity of satellite imagery for surficial material mapping.